infinite-ai-web - GitLite

KO | EN

gitlite — search

#kotlin #electron #computer-vision #privacy #devops #animation #linux #large-language-models #database #windows

infinite-ai-web

(★ 10)

No description available.

파일 탐색기

ZIP 다운로드

- - static.yml
- 1-enhancing-infinite-ai-web.md
- fbi_memo_v01.png
- fbi_memo_v1.png
- - fbi.html
- - modules.html
- favicon.ico.html
- fbi.html
- helo.html
- python.html
.gitattributes
.gitignore
config.py
home.html
index.html
infinite_web.py
models.py
project_tree.md
README.md
requirements.txt
templates.py
utils.py
views.py
web_folder_cleaner.py

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

명령어 용어집

이 문서에서 사용된 명령어를 모아봤습니다. 낯선 명령어가 있다면 펼쳐서 확인해보세요.

🔍

`pip install`

설명 보기 ▼

Install Python packages.

pip install {{package1 package2 ...}}

Install one or more packages:

pip install {{package1 package2 ...}} {{[-U|--upgrade]}}

Upgrade all specified packages to the latest version, installing any that are not already present:

pip install {{package}}=={{version}}

Install a specific version of a package:

🔍

`python`

설명 보기 ▼

Python 언어 인터프리터.
더 많은 정보: <https://docs.python.org/using/cmdline.html>.

python

REPL(대화형 셸) 시작:

python {{path/to/file.py}}

특정 Python 파일 실행:

python -i {{path/to/file.py}}

특정 Python 파일 실행 후 REPL 시작:

# 프로젝트 배지

chrome_qRkv6DD4mS

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

A dynamic web content generator that creates pages on-the-fly using AI. Simply search for any topic or navigate to any URL path, and the application will generate relevant content for that route.

## 📈 Development

### v0.1

![screenshot_fbi_memo_v01](https://raw.githubusercontent.com/TheLime1/infinite-ai-web/main/screenshots/fbi_memo_v01.png)

### v1

![screenshot_fbi_memo_v1](https://raw.githubusercontent.com/TheLime1/infinite-ai-web/main/screenshots/fbi_memo_v1.png)

## 🌟 Features

- **AI-Generated Content**: Uses Google's Gemini 2.0 Flash model to generate HTML content for any URL path.
- **Dynamic Routing**: Visit any URL path to get AI-generated content specifically for that path.
- **Search Interface**: Simple search functionality that redirects to the generated content.
- **Content Persistence**: Automatically saves generated content to the filesystem for faster access in future requests.
- **Organized Structure**: Maintains proper directory structure based on URL paths.
- **Index of Saved Content**: Automatically generates an index of all saved pages.

## 🚀 Getting Started

### Prerequisites

- Python 3.7 or higher
- Google Gemini API key

### Installation

1. Clone this repository:
   ```
   https://github.com/TheLime1/infinite-ai-web
   cd infinite-ai-web
   ```

2. Install the required dependencies:
   ```
   pip install -r requirements.txt
   ```

3. Create a `.env` file in the project root with your Google Gemini API key:
   ```
   GEMINI_API_KEY=your_api_key_here
   ```

### Running the Application

Run the Flask application:
```
python infinite_web.py
```

The server will start at http://localhost:5000 by default.

## 🧭 Usage

1. **Homepage**: Visit the root URL `/` to see the search interface.
2. **Direct Path Navigation**: Enter any path like `/python-tutorial` or `/history/ancient-rome` in your browser to generate content for that topic.
3. **Search**: Use the search box to look for a topic. The search will convert your query to a URL path and generate content.
4. **View Saved Pages**: Click on "Saved Searches" to see an index of all previously generated pages.

## ⚙️ How It Works

1. When a user visits a URL path, the application first checks if content has been previously generated and saved.
2. If found, the application serves the saved content.
3. If not found, the application generates the content using the Gemini AI model.
4. The AI-generated content is then saved to the file system for future requests.
5. The application maintains a proper directory structure that matches the URL path structure.

## 🛣️ Roadmap

- [ ] generate more complex content
- [ ] generate images
- [ ] toggle between different AI models
- [ ] generate links to external sources
- [ ] generate links that go deeper into the topic
- [ ] automate HTML dumbing to another repo with a cron job
- [ ] make diffrent colors for links (links not generated yet vs links generated and saved vs external links)

## 👁️ Observations : Model Comparison

| Model                | Speed  | Complexity | Image Generation |
| -------------------- | ------ | ---------- | ---------------- |
| Gemini 2.0 Flash     | Fast   | Medium     | No               |
| Gemini 1.5 Flash Exp | Medium | High       | Yes              |
| Gemini 1.5 Pro       | Slow   | High       | didnt test yet   |

## 🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.